Water conservancy project construction monitoring data supervision system and method based on multi-source data fusion

Abstract

The invention discloses a water conservancy project construction monitoring data supervision system and method based on multi-source data fusion, and relates to the technical field of engineering construction. The multi-source data fused hydraulic engineering construction monitoring data supervision system and method comprises the following steps: S1, acquiring hydraulic engineering construction monitoring data, and preprocessing the hydraulic engineering construction monitoring data; s2, constructing a sliding window, extracting key structure and environment variables, comprehensively analyzing a structure disturbance degree, and dividing different disturbance state sections according to the structure disturbance degree; s3, an unstable state time period is extracted, a disturbance feature sequence is constructed, highly-suspected disturbance fragments are identified, response deviation between the structure and the environment is analyzed, highly-credible abnormal fragments are screened, and an abnormal data structure is generated; and S4, the coupling relation between the structural response and the environmental disturbance is analyzed in a combined mode, and a dynamic unbalance index used for measuring the unsteady state intensity is constructed. The problem that the abnormal recognition false alarm rate is high due to the fact that monitoring data are disturbed frequently in a complex construction scene is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering construction, and in particular to a water conservancy project construction monitoring data supervision system and method that integrates multi-source data. Background Art

[0002] As water conservancy projects continue to expand in scale and complexity, intelligent, sophisticated monitoring methods are gradually replacing traditional, experience-based, manual management. The widespread deployment of multi-source sensing equipment is enriching on-site monitoring data, and continuous advancements in engineering technology research and development are providing algorithmic and systemic support for data-driven structural health analysis models and monitoring decision-making mechanisms.

[0003] For example, the invention with announcement number: CN118761637A discloses a method for safety supervision of water conservancy and hydropower project construction, which relates to the field of engineering construction technology, and includes the following method: the environmental risk level value during construction, the complexity value of construction technology and the number of defects in construction management are input into the supervision module, and the supervision module outputs a comprehensive risk index, a response capability index and a safety performance index.

[0004] For example, the invention with publication number: CN116090822A discloses a water conservancy construction safety protection supervision system based on data analysis, including a main control module, a data acquisition module, a safety monitoring module, a pre-deployment module and a risk warning module; by weighting the temporary power supply areas in various water conservancy construction locations, key monitoring objects are determined, and targeted monitoring and analysis are carried out on the key monitoring objects. At the same time, according to the water conservancy construction nodes where each temporary power supply area is located, the temporary power supply areas that may appear in the future are determined.

[0005] However, in actual water conservancy construction, due to the complex construction environment and diverse disturbance factors, existing monitoring systems often suffer from delayed anomaly identification, high false alarm rates, and fragmented data processing chains. The development of relevant engineering technologies remains weak, making it difficult to effectively support the refined safety management needs under dynamic conditions. Especially in the early stages of a disturbance event, the coupling relationship between structural response and environmental changes has not been fully characterized, making it difficult to capture key risk signals in a timely manner.

[0006] Therefore, in response to the above problems, there is an urgent need for a water conservancy project construction monitoring data supervision system and method that integrates multi-source data. Summary of the Invention

[0007] Technical problems solved

[0008] In response to the shortcomings of the existing technology, the present invention provides a water conservancy project construction monitoring data supervision system and method with multi-source data fusion, which solves the problem of high false alarm rate of abnormal identification due to frequent interference of monitoring data in complex construction scenarios.

[0009] Technical Solution

[0010] To achieve the above objectives, the present invention is implemented through the following technical solutions: a multi-source data fusion water conservancy project construction monitoring data supervision system and method, comprising the following steps: S1, acquiring water conservancy construction monitoring data by real-time data acquisition and synchronous processing of multiple types of sensor equipment in the construction monitoring system, and preprocessing the water conservancy construction monitoring data to obtain preprocessed water conservancy construction monitoring data; S2, constructing a sliding window based on the preprocessed water conservancy construction monitoring data, extracting key structural and environmental variables, comprehensively analyzing the degree of structural disturbance, dividing different disturbance state segments according to the degree of structural disturbance, and marking the segment state labels of each time period; S3, extracting unstable time periods based on the segment state labels, constructing disturbance feature sequences, identifying highly suspected disturbance segments, and analyzing the response deviation between the structure and the environment, combining the three-dimensional structural response sequence with historical steady-state samples for sliding comparison, screening highly reliable abnormal segments, and generating an abnormal data structure; S4, based on the identified abnormal data structure, jointly analyzing the coupling relationship between the structural response and the environmental disturbance, constructing a dynamic imbalance index for measuring the intensity of the unstable state, classifying the abnormality level according to the dynamic imbalance index, and updating the corresponding scheduling strategy and acquisition configuration.

[0011] Furthermore, by collecting and synchronously processing the real-time data of various types of sensor equipment in the construction monitoring system, the specific steps for obtaining water conservancy construction monitoring data are as follows: by collecting and synchronously processing the real-time data of various types of sensor equipment in the construction monitoring system, water conservancy construction monitoring data are obtained, and the water conservancy construction monitoring data include pore water pressure, seepage rate, atmospheric pressure, construction temperature, construction humidity, surface settlement, concrete crack width, stress value of load-bearing components, steel bar stress, and structural vibration acceleration; among them, the pore water pressure is obtained by reading the liquid static pressure change collected by the piezometers buried in the dam foundation and slope; the seepage rate is obtained by reading the flow rate conversion result output by the seepage pressure difference sensor; the seepage rate is obtained by reading the flow rate conversion result output by the seepage pressure difference sensor installed in the dam foundation and slope ... The air pressure module in the field meteorological unit measures the atmospheric pressure in real time; the construction temperature and humidity are obtained through the temperature channel and humidity channel data output by the environmental sensor node; the surface settlement is obtained by reading the coordinate change information of the measuring point of the global navigation satellite system and combining it with the elevation difference extracted from the leveling measurement; the concrete crack width is obtained by collecting the displacement measurement value between two points of the crack sensor; the stress value of the load-bearing component is obtained by reading the electrical signal collected by the stress sensor embedded in the load-bearing structure and calibrating it. The steel bar stress is obtained by collecting the data of the strain gauge on the steel bar surface and combining it with the steel bar elastic modulus conversion; the structural vibration acceleration is obtained by reading the instantaneous acceleration value output by the three-axis acceleration sensor.

[0012] Furthermore, the water conservancy construction monitoring data is preprocessed to obtain the preprocessed water conservancy construction monitoring data. The specific steps are as follows: through the collaborative detection of the standard deviation outlier detection method based on the sliding window and the isolation forest algorithm, the sudden changes and link abnormal data in the pore water pressure, seepage rate and structural vibration acceleration are identified and eliminated; by utilizing the combined completion mechanism of the time series linear interpolation method and the spline interpolation algorithm, the missing fields in the surface settlement, construction humidity and concrete crack width are completed in time series; through the joint modeling strategy of fusing the exponential weighted sliding average and the local regression algorithm, the construction temperature, steel bar stress and load-bearing component stress values ​​are trend fitted and high-frequency noise is suppressed; by adopting the cascade transformation of the power function transformation and the maximum and minimum normalization algorithm, the water conservancy construction monitoring data is distributed adjusted and numerically compressed, and the unified interval reconstruction and normalization processing of the water conservancy construction monitoring data are completed.

[0013] Furthermore, based on the pre-processed water conservancy construction monitoring data, a sliding window is constructed to extract key structural and environmental variables, and the specific steps for comprehensively analyzing the degree of structural disturbance are as follows: the time series of pre-processed pore water pressure, seepage rate, atmospheric pressure, construction temperature, construction humidity, surface settlement, concrete crack width, stress value of load-bearing components, steel bar stress and structural vibration acceleration are aligned according to a unified sampling time, and merged according to the monitoring point number to form a multidimensional data structure with a unified time series and spatial index; a sliding window of fixed length is defined in the multidimensional data structure, and the concrete crack width, stress value of load-bearing components, steel bar stress and structural vibration acceleration within the sliding window are extracted. The disturbance degree of water conservancy project structure under complex construction and environmental conditions is evaluated by taking into account the following factors: the square of the concrete crack width is divided by the crack width threshold, the absolute value of the difference between the stress value of the load-bearing component and the stress of the steel bar is calculated, and the first part is obtained by adding this ratio to the sum of the absolute values ​​and multiplying it by the structural weight; the absolute value of the difference between the pore water pressure and the atmospheric pressure is calculated, and the sum of the construction temperature, construction humidity and the minimum term is calculated, and the second part is obtained by dividing this absolute value by the ratio of the sum and multiplying it by the environmental weight; the first and second parts are added together to obtain the structural disturbance assessment value.

[0014] Furthermore, different disturbance state segments are divided according to the degree of structural disturbance, and the specific steps of marking the segment state labels of each time period are as follows: the structural disturbance assessment value in each sliding window is calculated in real time, and the structural disturbance assessment value is compared with the structural disturbance threshold. The structural disturbance threshold includes the first-level structural disturbance threshold and the second-level structural disturbance threshold: when the structural disturbance assessment value is less than or equal to the first-level structural disturbance threshold, the current time period is marked as a steady-state segment, and the baseline update strategy is automatically triggered. The original water conservancy construction monitoring data in the current window is incrementally updated in the steady-state sample set, and statistical feature regression is performed. When the structural disturbance assessment value is greater than the primary structural disturbance threshold and less than the secondary structural disturbance threshold, the current time period is marked as a transition section, the delayed confirmation mechanism is activated, all water conservancy construction monitoring data in the current window is retained, and a time buffer is set for subsequent state evolution trend judgment; when the structural disturbance assessment value is greater than or equal to the secondary structural disturbance threshold, the current time period is marked as an unstable section, the high-frequency re-sampling logic is called, and the enhanced sampling mode is enabled for the covered monitoring points in the subsequent time period, and the water conservancy construction monitoring data in the current sliding window is pushed to the anomaly identification processing process;

[0015] The segment mark corresponding to each time period is used as the segment status label and attached to the metadata of the current sliding window. The label contains the status category, time segment range and monitoring point number, and is retained together with the time index and used as the input index and scheduling basis for the subsequent recognition process.

[0016] Furthermore, based on the segment state label, the unstable time period is extracted, the disturbance feature sequence is constructed, the highly suspected disturbance segments are identified and the response deviation between the structure and the environment is analyzed. The specific steps are as follows: the time period in which the segment state label is marked as the unstable segment is extracted, the corresponding pore water pressure, seepage rate and structural vibration acceleration in the time period are obtained, and the pseudo-anomaly candidate sample set is constructed by combining the time index and monitoring point number contained in the state label; in the pseudo-anomaly candidate sample set, a sliding time series is constructed around the pore water pressure, seepage rate and structural vibration acceleration, and three types of statistical features are extracted: standard deviation, jump amplitude and number of fluctuations; each statistical feature is normalized to form a feature vector and input into the data set. The isolation forest algorithm is used to calculate the corresponding isolation value. The isolation value is compared with the isolation judgment threshold in real time, and samples with isolation values ​​exceeding the isolation judgment threshold are screened out and recorded as highly suspected disturbance fragments. For highly suspected disturbance fragments, the degree of deviation between their internal structural response and the external environmental background is further quantified. The absolute value of the difference between the stress value of the load-bearing component and the stress of the steel bar is divided by the sum of the concrete crack width and the minimum term, and the ratio is recorded as the structural coordination term. The absolute value of the difference between the pore water pressure and the atmospheric pressure is calculated, added to 1, and the logarithm is taken. The structural vibration acceleration is divided by this logarithm value plus 1, and the ratio is added to 1 as the disturbance amplification term. The structural coordination term is multiplied by the disturbance amplification term to obtain the structural response deviation value.

[0017] Furthermore, the specific steps of combining the three-dimensional structural response sequence with the historical steady-state samples for sliding comparison, screening high-confidence abnormal fragments and generating abnormal data structures are as follows: the calculated structural response deviation value is compared with the response deviation threshold. When the structural response deviation value is less than the response deviation threshold, the highly suspected disturbance fragment is marked as a pseudo-anomaly candidate and retained for subsequent pseudo-anomaly statistical analysis; when the structural response deviation value is greater than or equal to the response deviation threshold, the highly suspected disturbance fragment is transferred to the next step of feature pattern comparison, and the spectrum similarity analysis is performed: the concrete crack width, stress value of the load-bearing component and steel stress of the current highly suspected disturbance fragment are extracted to form a pseudo-anomaly candidate. The three-dimensional structural response sequence is slidingly matched with the stable three-dimensional structural response sequence composed of concrete crack width, load-bearing component stress and steel bar stress in the historical steady-state sample set; if the structural response threshold error range constraint is met in the continuous comparison segment, the current highly suspected disturbance segment is marked as a steady-state deviation; otherwise, the current highly suspected disturbance segment is marked as a highly credible anomaly segment; the water conservancy construction monitoring data corresponding to the time segment identified as a highly credible anomaly segment are recorded together with the time index, monitoring point number, structural disturbance assessment value and structural response deviation value to form a complete anomaly data structure, which serves as the input basis for the subsequent anomaly analysis and judgment process.

[0018] Furthermore, based on the identified abnormal data structure, the coupling relationship between structural response and environmental disturbance is jointly analyzed, and the specific steps for constructing a dynamic imbalance index for measuring non-steady-state intensity are as follows: based on the abnormal data structure, all water conservancy construction monitoring data of the time period corresponding to the high-credible abnormal segment are extracted, and the structural disturbance assessment value and the structural response deviation value are combined to comprehensively analyze the coupling mode between the structural response and the environmental disturbance, and quantify the non-steady-state driving intensity of the current time period; the square of the sum of the structural disturbance assessment value and the structural response deviation value is calculated, and recorded as the structural response amplification term; the product of the surface settlement and the seepage rate is calculated, and this product is divided by the construction temperature plus the minimum term, and the ratio is recorded as the geological environment coupling term; the absolute value of the difference between the pore water pressure and the atmospheric pressure is calculated and added to 1, and the logarithm of this logarithm is recorded as the external pressure disturbance adjustment term; the structural response amplification term, the geological environment coupling term and the external pressure disturbance adjustment term are added together to obtain the dynamic imbalance value.

[0019] Furthermore, the abnormality levels are divided according to the dynamic imbalance index, and the specific steps for updating the corresponding scheduling strategy and acquisition configuration are as follows: after calculating the dynamic imbalance value, the dynamic imbalance value and the imbalance threshold are compared in real time, and the high-credibility abnormal fragments are divided into levels; wherein, the imbalance threshold includes the first-level imbalance threshold and the second-level imbalance threshold; when the dynamic imbalance value is less than or equal to the first-level imbalance threshold, the current high-credibility abnormal fragment is marked as a mild disturbance, triggering the local re-sampling logic, and performing encrypted sampling on the current monitoring point; when the dynamic imbalance value is greater than the first-level imbalance threshold and less than the second-level imbalance threshold, the current high-credibility abnormal fragment is marked as a critical disturbance, and the current monitoring point is encrypted and sampled, and the water conservancy monitoring data corresponding to the current high-credibility abnormal fragment is pushed to the supervision platform, with additional manual review prompts; when the dynamic imbalance value is greater than the first-level imbalance threshold and less than the second-level imbalance threshold, the current high-credibility abnormal fragment is marked as a critical disturbance, and the current monitoring point is encrypted and sampled, and the water conservancy monitoring data corresponding to the current high-credibility abnormal fragment is pushed to the supervision platform, with additional manual review prompts; When the dynamic imbalance value is greater than or equal to the second-level imbalance threshold, the current high-confidence abnormal fragment is marked as a severe disturbance, triggering the entire station alarm process, suspending related construction tasks, and transferring the fragment data to the abnormal tracing process; the dynamic imbalance value, abnormal level label, scheduling processing record and corresponding time index are archived to generate an abnormal event log, which is bound to the original water conservancy construction monitoring data to achieve full-process index tracing; the abnormal level, dynamic imbalance value, structural disturbance assessment value and structural response deviation value marked in the abnormal event log are synchronously written into the acquisition and scheduling configuration table for updating the sampling frequency setting, monitoring point priority sorting and comparison threshold adjustment plan, realizing adaptive scheduling optimization based on the actual abnormal evolution characteristics, and completing the closed-loop process of monitoring identification, response control and acquisition strategy.

[0020] The second aspect of the present invention provides a water conservancy project construction monitoring data supervision system with multi-source data fusion, including: a water conservancy construction monitoring data acquisition and preprocessing module, a structural disturbance assessment and status marking module, a disturbance identification and abnormal sample extraction module and an abnormal analysis judgment and scheduling linkage module, wherein: the water conservancy construction monitoring data acquisition and preprocessing module is used to obtain water conservancy construction monitoring data through real-time data acquisition and synchronous processing of multiple types of sensor equipment in the construction monitoring system, and preprocess the water conservancy construction monitoring data to obtain preprocessed water conservancy construction monitoring data; the structural disturbance assessment and status marking module is used to construct a sliding window based on the preprocessed water conservancy construction monitoring data, extract key structural and environmental variables, and comprehensively analyze the results. The system divides the structural disturbance degree into different disturbance state segments according to the structural disturbance degree and marks the segment state labels of each time period; the disturbance identification and abnormal sample extraction module is used to extract the unstable time period based on the segment state label, construct the disturbance feature sequence, identify the highly suspected disturbance fragments and analyze the response deviation between the structure and the environment, combine the three-dimensional structural response sequence with the historical steady-state samples for sliding comparison, screen the highly reliable abnormal fragments and generate the abnormal data structure; the abnormal analysis and judgment and scheduling linkage module is used to jointly analyze the coupling relationship between the structural response and the environmental disturbance based on the identified abnormal data structure, construct the dynamic imbalance index for measuring the non-steady-state intensity, divide the abnormal level according to the dynamic imbalance index, and update the corresponding scheduling strategy and acquisition configuration.

[0021] Beneficial effects

[0022] The present invention has the following beneficial effects:

[0023] (1) This multi-source data fusion water conservancy project construction monitoring data supervision system and method constructs a structural disturbance assessment value, integrates water conservancy construction monitoring data, and analyzes disturbance trends in real time within a sliding window. This indicator can distinguish between three types of section states: steady state, transition, and unstable state, effectively supporting the pre-identification and state classification of early disturbances. Its introduction realizes the quantitative expression of disturbance intensity, circumventing the problem of traditional methods that highly rely on empirical thresholds and single-point monitoring data for abnormal judgment, and provides a precise entry point for subsequent high-frequency sampling scheduling and abnormal screening.

[0024] (2) The multi-source data fusion water conservancy project construction monitoring data supervision system and method, by relying on the combined relationship of steel bar stress, load-bearing component stress, concrete crack width, structural vibration acceleration, pore water pressure and atmospheric pressure to perform deviation modeling, obtains the structural response deviation value, which not only reflects the degree of reaction of the disturbance influence inside the structure, but also reflects the amplification effect of external disturbance factors on the structural state. It is a further accurate screening after the disturbance assessment, effectively improves the recognition accuracy of high-confidence abnormal fragments, and provides key input for the subsequent imbalance level classification.

[0025] (3) The multi-source data fusion water conservancy project construction monitoring data supervision system and method, by constructing a dynamic imbalance value, integrates key variables such as structural disturbance assessment value, structural response deviation value, surface settlement, seepage rate, pore water pressure, atmospheric pressure, etc., and further characterizes the coupling relationship between the disturbance source and the response mechanism on the basis of abnormal state identification. It breaks through the limitation of the traditional monitoring system of separating the structural behavior and environmental changes, and can dynamically reflect the linkage between different monitoring data, providing a quantitative basis for state perception and trend analysis under complex construction conditions.

[0026] (4) The multi-source data fusion water conservancy project construction monitoring data supervision system and method automatically integrates high-confidence abnormal fragments with multi-source information such as time index, monitoring point number, structural disturbance assessment value, and structural response deviation value after identifying them to construct a structured abnormal data object. This data structure not only retains the original monitoring data, but also associates the analysis logic and calculation results in the entire identification chain, providing a reliable foundation for subsequent tracing and troubleshooting, event restoration, manual verification, and model optimization, thus achieving closed-loop support from abnormal information discovery to interpretation. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A flow chart of the data supervision method for water conservancy project construction monitoring with source data fusion;

[0028] Figure 2 This is the structural diagram of the water conservancy project construction monitoring data supervision system with source data fusion;

[0029] Figure 3 The distribution diagram of structural disturbance assessment value in each time period;

[0030] Figure 4 This is the distribution diagram of dynamic imbalance value and disturbance level of high-confidence abnormal fragments. DETAILED DESCRIPTION

[0031] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0032] See also Figure 1-Figure 4The embodiment of the present invention provides a technical solution: a water conservancy project construction monitoring data supervision system and method using multi-source data fusion, comprising the following steps: S1, acquiring water conservancy construction monitoring data by real-time data collection and synchronous processing of multiple types of sensor equipment in the construction monitoring system, and preprocessing the water conservancy construction monitoring data to obtain preprocessed water conservancy construction monitoring data; S2, constructing a sliding window based on the preprocessed water conservancy construction monitoring data, extracting key structural and environmental variables, comprehensively analyzing the degree of structural disturbance, dividing different disturbance state segments according to the degree of structural disturbance, and marking the segment state labels of each time period; S3, extracting unstable time periods based on the segment state labels, constructing disturbance feature sequences, identifying highly suspected disturbance segments, and analyzing the response deviation between the structure and the environment, combining the three-dimensional structural response sequence with historical steady-state samples for sliding comparison, screening highly reliable abnormal segments, and generating an abnormal data structure; S4, based on the identified abnormal data structure, jointly analyzing the coupling relationship between the structural response and the environmental disturbance, constructing a dynamic imbalance index for measuring the intensity of the unstable state, classifying the abnormality level according to the dynamic imbalance index, and updating the corresponding scheduling strategy and acquisition configuration.

[0033] Specifically, the specific steps for obtaining water conservancy construction monitoring data through real-time data collection and synchronous processing of multiple types of sensor equipment in the construction monitoring system are as follows: water conservancy construction monitoring data are obtained through real-time data collection and synchronous processing of multiple types of sensor equipment in the construction monitoring system. The water conservancy construction monitoring data include pore water pressure, seepage rate, atmospheric pressure, construction temperature, construction humidity, surface settlement, concrete crack width, stress value of load-bearing components, steel bar stress, and structural vibration acceleration; among them, the pore water pressure is obtained by reading the liquid static pressure changes collected by the piezometers buried in the dam foundation and slopes; the seepage rate is obtained by reading the flow rate conversion result output by the seepage pressure difference sensor; and the seepage rate is obtained by reading the flow rate conversion result output by the seepage pressure difference sensor installed on site. The air pressure module in the meteorological unit measures the atmospheric pressure in real time; the construction temperature and humidity are obtained through the temperature channel and humidity channel data output by the environmental sensor node; the surface settlement is obtained by reading the coordinate change information of the measuring point of the global navigation satellite system and combining it with the elevation difference extracted from the leveling measurement; the concrete crack width is obtained by collecting the displacement measurement value between two points of the crack sensor; the stress value of the load-bearing component is obtained by reading the electrical signal collected by the stress sensor embedded in the load-bearing structure and calibrating it. The steel bar stress is obtained by collecting the data of the strain gauge on the steel bar surface and combining it with the steel bar elastic modulus conversion; the structural vibration acceleration is obtained by reading the instantaneous acceleration value output by the three-axis acceleration sensor.

[0034] In this implementation plan, through real-time data collection and synchronous processing of multiple types of sensing equipment in the construction monitoring system, comprehensive acquisition of key water conservancy construction monitoring data such as pore water pressure, seepage rate, atmospheric pressure, construction temperature, construction humidity, surface settlement, concrete crack width, stress values ​​of load-bearing components, steel bar stress, and structural vibration acceleration is achieved, ensuring multi-dimensional information coverage of structural response, geological changes, and environmental conditions. By separately reading different types of equipment such as piezometers, seepage pressure differential sensors, air pressure modules, environmental sensing nodes, global navigation satellite system measurement points, leveling equipment, crack sensors, stress sensors, strain gauges, and triaxial accelerometers, the sources of each monitoring data item are separated, indicators are clearly defined, and data consistency is controlled, providing a stable and accurate data foundation for subsequent anomaly identification, disturbance assessment, and scheduling linkage.

[0035] Specifically, the steps for preprocessing water conservancy construction monitoring data to obtain preprocessed water conservancy construction monitoring data are as follows: through the collaborative detection of the standard deviation outlier detection method based on a sliding window and the isolation forest algorithm, sudden changes and link anomalies in pore water pressure, seepage rate, and structural vibration acceleration are identified and eliminated, ensuring the reliability of the source data in terms of temporal continuity and transmission stability. By utilizing a combined completion mechanism of the time series linear interpolation method and the spline interpolation algorithm, the missing fields in surface settlement, construction humidity, and concrete crack width are time-series completed, and the missing source identifiers are retained to support the traceability of subsequent processing nodes. Through a joint modeling strategy integrating the exponentially weighted moving average and the local regression algorithm, trend fitting and high-frequency noise suppression are performed on the construction temperature, steel bar stress, and load-bearing component stress values, reducing false triggering interference of the monitoring data while retaining the abnormal structural response characteristics. Through the cascade transformation of the power function transformation and the maximum and minimum normalization algorithm, the water conservancy construction monitoring data are distributed adjusted and numerically compressed, completing the scale unification and normalization of the water conservancy construction monitoring data without losing the characteristic structure of the original data.

[0036] This implementation establishes a robust preprocessing mechanism for addressing data stability and integrity issues in complex scenarios by removing outliers in pore water pressure, seepage rate, and structural vibration acceleration; completing missing values ​​for ground settlement, construction humidity, and concrete crack width; performing trend fitting and noise reduction on construction temperature, steel bar stress, and stress values ​​of loaded components; and normalizing and reconstructing all water conservancy construction monitoring data. Supported by engineering technology research and development, this mechanism not only improves the availability and consistency of water conservancy construction monitoring data but also provides a reliable data foundation for subsequent structural disturbance assessment and anomaly identification, ensuring the monitoring system's effective data support capabilities under non-steady-state conditions.

[0037] Specifically, a sliding window is constructed based on the preprocessed water conservancy construction monitoring data, key structural and environmental variables are extracted, and the specific steps for comprehensively analyzing the degree of structural disturbance are as follows: the time series of preprocessed pore water pressure, seepage rate, atmospheric pressure, construction temperature, construction humidity, surface settlement, concrete crack width, stress value of load-bearing components, steel bar stress and structural vibration acceleration are aligned according to a unified sampling time, and merged according to the monitoring point number to form a multidimensional data structure with a unified temporal and spatial index, and provide consistent input conditions for dynamic comparative analysis between different monitoring points; in this multidimensional data structure, a sliding window of fixed length is defined to ensure the continuity and comparability of structural disturbance information in the time domain. Subsequently, the concrete crack width, stress value of the load-bearing component, steel stress, pore water pressure, atmospheric pressure, construction temperature, and construction humidity within the sliding window were extracted as key structural and environmental variables. Combined with the crack width threshold as a basic reference for structural response anomalies, the degree of disturbance of the water conservancy project structure under complex construction and environmental conditions was assessed: the square of the concrete crack width was calculated and divided by the crack width threshold to measure the degree of crack extension anomaly. The absolute value of the difference between the load-bearing component stress value and the steel stress was calculated to reflect the internal mechanical transmission deviation of the structure. The first part was obtained by adding the absolute value of the difference between the load-bearing component stress value and the steel stress value, and multiplying it by the structural weight. The absolute value of the difference between the pore water pressure and the atmospheric pressure was calculated to characterize the impact of external hydrological disturbances. The environmental factor adjustment term was constructed by calculating the sum of the construction temperature, construction humidity, and the minimum term. The minimum term is a set decimal constant used to avoid numerical anomalies with a denominator of zero and ensure calculation stability. The second part was obtained by dividing the absolute value by the ratio of the sum value and multiplying it by the environmental weight. The first and second parts were added together to obtain the structural disturbance assessment value, which serves as the basic indicator for subsequent state classification and anomaly identification. Among them, the least squares regression algorithm is used to fit the joint change relationship of concrete crack width, load-bearing component stress value, steel bar stress, pore water pressure, atmospheric pressure, construction temperature and construction humidity in multiple time periods in historical monitoring data to obtain the structural weight and environmental weight. The value range of the structural weight and environmental weight is [1,0].

[0038] The specific calculation formula for the structural disturbance assessment value is:

[0039]

[0040] Where D represents the structural disturbance assessment value, α represents the structural weight, β represents the environmental weight, and W c Indicates the width of concrete crack, W r represents the crack width threshold, σ s Represents the stress value of the load-bearing component, σ r represents the steel bar stress, P w represents the pore water pressure, P arepresents atmospheric pressure, T represents construction temperature, RH represents construction humidity, and ∈ represents a minimum term.

[0041] In this embodiment, Table 1 is a structural disturbance assessment value data table, which records in detail the key monitoring variables and structural disturbance assessment value calculation results in the structural disturbance modeling and analysis process in five different time periods, and is used to measure the stability state of the structural response under complex construction and environmental conditions. Among them: in time period 1, the concrete crack width is 0.35, the structural weight is 0.5, the stress value of the load-bearing component is 18.5, the stress value of the steel bar is 17.9, the pore water pressure is 105.4, the atmospheric pressure is 101.3, the construction temperature is 28.5, the construction humidity is 74.3, and the structural disturbance assessment value is 0.52; in time period 2, the concrete crack width is 0.28, the structural weight is 0.5, the stress value of the load-bearing component is 16.2, the stress value of the steel bar is 15.7, the pore water pressure is 97.2, the atmospheric pressure is 101.3, the construction temperature is 27.2, the construction humidity is 70.5, and the structural disturbance assessment value is 0.41; in time period 3, the concrete crack width is 0.42, the structural weight is 0.5, the stress value of the load-bearing component is 19.8, the stress value of the steel bar is 19.1, The pore water pressure was 112.6, the atmospheric pressure was 101.3, the construction temperature was 29.6, the construction humidity was 76.8, and the structural disturbance assessment value was 0.67; in time period 4, the concrete crack width was 0.33, the structural weight was 0.5, the stress value of the load-bearing component was 17.3, the steel stress was 16.9, the pore water pressure was 101.8, the atmospheric pressure was 101.3, the construction temperature was 26.8, the construction humidity was 72.4, and the structural disturbance assessment value was 0.37; in time period 5, the concrete crack width was 0.31, the structural weight was 0.5, the stress value of the load-bearing component was 16.7, the steel stress was 16.2, the pore water pressure was 99.5, the atmospheric pressure was 101.3, the construction temperature was 27.9, the construction humidity was 71.6, and the structural disturbance assessment value was 0.42.

[0042] Table 1 Structural disturbance assessment value data table

[0043] Time period <![CDATA[W c ]]> <![CDATA[W r ]]> <![CDATA[σ s ]]> <![CDATA[σ r ]]> <![CDATA[P w ]]> <![CDATA[P a ]]> T RH D Time period 1 0.35 0.5 18.5 17.9 105.4 101.3 28.5 74.3 0.52 Time period 2 0.28 0.5 16.2 15.7 97.2 101.3 27.2 70.5 0.41 Time period 3 0.42 0.5 19.8 19.1 112.6 101.3 29.6 76.8 0.67 Time period 4 0.33 0.5 17.3 16.9 101.8 101.3 26.8 72.4 0.37 Time period 5 0.31 0.5 16.7 16.2 99.5 101.3 27.9 71.6 0.42

[0044] like Figure 3 The figure below shows the distribution of structural perturbation assessment values ​​for each time period, providing a visual overview of the distribution of these values. The figure displays the structural perturbation assessment values ​​for five different time periods, ranging from 0.37 to 0.67. Time period 3 has the highest perturbation value, reaching 0.67, reflecting a significant deviation in the coupling between the structural forces and the environment during this period. Time period 4 has the lowest perturbation value, at only 0.37, indicating a relatively stable state. This distribution of structural perturbation assessment values ​​for each time period helps clearly identify perturbation trends and provides a quantitative basis for subsequent structural state identification and dynamic response strategy formulation.

[0045] In this implementation plan, by constructing a multidimensional data structure with a unified temporal and spatial index, a sliding window is defined and key structural and environmental variables such as concrete crack width, stress value of load-bearing components, steel bar stress, pore water pressure, atmospheric pressure, construction temperature and construction humidity are extracted. Combined with the crack width threshold, a structural disturbance assessment value is constructed to effectively reflect the degree of disturbance of water conservancy projects under complex construction conditions. This method not only ensures the continuity and comparability of structural disturbance characteristics in the time domain, but also enhances the engineering applicability of the calculation results by introducing structural weights and environmental weights and setting minimum terms to ensure numerical stability. Through the in-depth support of engineering technology research and development, it provides operational and quantifiable basic indicators for subsequent state division and anomaly identification, and improves the integrated analysis level of monitoring data and the sensitivity of on-site disturbance response.

[0046] Specifically, different disturbance state segments are divided according to the degree of structural disturbance, and the specific steps for marking the segment state labels of each time period are as follows: the structural disturbance assessment value in each sliding window is calculated in real time, and the structural disturbance assessment value is compared with the structural disturbance threshold. The structural disturbance threshold includes the first-level structural disturbance threshold and the second-level structural disturbance threshold: when the structural disturbance assessment value is less than or equal to the first-level structural disturbance threshold, the current time period is marked as a steady-state segment, and the baseline update strategy is automatically triggered. The original water conservancy construction monitoring data in the current window is incrementally updated in the steady-state sample set, and statistical features are archived. ; When the structural disturbance assessment value is greater than the first-level structural disturbance threshold and less than the second-level structural disturbance threshold, the current time period is marked as a transition section, the delayed confirmation mechanism is activated, all water conservancy construction monitoring data in the current window is retained, and a time buffer is set for subsequent state evolution trend judgment; when the structural disturbance assessment value is greater than or equal to the second-level structural disturbance threshold, the current time period is marked as an unstable section, the high-frequency re-sampling logic is called, and the enhanced sampling mode is enabled for the covered monitoring points in the subsequent time period, and the water conservancy construction monitoring data in the current sliding window is pushed to the anomaly identification processing process;

[0047] The segment mark corresponding to each time period is used as the segment status label and attached to the metadata of the current sliding window. The label contains the status category, time segment range and monitoring point number, and is retained together with the time index and used as the input index and scheduling basis for the subsequent recognition process.

[0048] In this implementation, by comparing the structural disturbance assessment value with the set primary and secondary structural disturbance thresholds in real time, the system dynamically divides the system into stable, transitional, and unstable sections. Differentiated processing strategies, such as baseline updates, delayed confirmation, and high-frequency re-sampling, are formulated for each section, enhancing adaptability to complex construction conditions and the pertinence of data management. Furthermore, by binding section status labels to sliding window metadata, recording status categories, time segment ranges, and monitoring point numbers, the system achieves traceable annotation and scheduling-driven structural disturbance status, providing an accurate and efficient input index basis for subsequent anomaly identification processes, improving the data closure capability and engineering response efficiency of the entire monitoring chain.

[0049] Specifically, the specific steps of extracting unstable time periods based on segment status labels, constructing disturbance feature sequences, identifying highly suspected disturbance segments and analyzing the response deviation between the structure and the environment are as follows: extracting time periods where the segment status labels are marked as unstable segments, obtaining the corresponding pore water pressure, seepage rate and structural vibration acceleration within the time period, and combining the time index and monitoring point number contained in the status label to construct a pseudo-anomaly candidate sample set to provide data source guarantee for subsequent anomaly detection; in the pseudo-anomaly candidate sample set, constructing a sliding time series around pore water pressure, seepage rate and structural vibration acceleration, extracting three types of statistical features, namely standard deviation, jump amplitude and number of fluctuations, to comprehensively reflect the severity and duration of disturbance changes; normalizing each statistical feature to form a feature vector, inputting the isolation forest algorithm to calculate the corresponding isolation value, and making full use of the unsupervised model to automatically characterize and score the non-steady-state disturbance behavior; comparing the isolation value and the isolation judgment threshold in real time, Samples with isolation values ​​exceeding the isolation threshold are screened out and recorded as highly suspected disturbance fragments, serving as the basis for subsequent deviation quantification analysis. For highly suspected disturbance fragments, the degree of deviation between their internal structural response and the external environmental background is further quantified to improve the basis for disturbance identification. The absolute value of the difference between the stress value of the load-bearing component and the stress of the steel bar is divided by the sum of the concrete crack width and the minimum term, and the ratio is recorded as the structural coordination term, reflecting the internal consistency of the structural mechanical behavior. The minimum term is used to prevent abnormal calculation results caused by a zero denominator. The absolute value of the difference between the pore water pressure and the atmospheric pressure is calculated, added to 1, and then the logarithm is taken to construct the hydrological disturbance amplification adjustment term. The structural vibration acceleration is then divided by this logarithmic value plus 1. This ratio, added to 1, is used as the disturbance amplification term to quantify the amplification effect of external disturbances on structural behavior. Finally, the structural coordination term is multiplied by the disturbance amplification term to obtain the structural response deviation value, which provides a key basic indicator for subsequent high-confidence abnormal fragment identification and dynamic imbalance strength assessment.

[0050] Among them, the specific calculation formula of the structural response deviation value is:

[0051]

[0052] Where S represents the structural response deviation value, σ s Represents the stress value of the load-bearing component, σ r represents the steel bar stress, W c represents the width of concrete cracks, ∈ represents the minimum term, a represents the structural vibration acceleration, P w represents the pore water pressure, P a Indicates atmospheric pressure.

[0053] In this implementation, the sensitivity and robustness of non-steady-state behavior identification are enhanced by constructing a set of pseudo-anomaly candidate samples, extracting key statistical features of pore water pressure, seepage rate, and structural vibration acceleration, and combining them with the isolation forest algorithm to effectively screen highly suspected disturbance fragments. Furthermore, the structural coordination term and the disturbance amplification term are introduced to jointly quantify the amplified effects of the internal mechanical consistency of the structure and the external hydrological environment, ultimately generating a structural response deviation value. This provides a clear analytical basis for further classification of anomaly fragments and assessment of dynamic imbalance, and enhances the diagnostic capabilities of structure-environment coupled disturbances. This method possesses strong data adaptability and analytical scalability, providing precise support for the subsequent design of anomaly management strategies.

[0054] Specifically, the specific steps of combining the three-dimensional structural response sequence with the historical steady-state samples for sliding comparison, screening high-confidence abnormal fragments and generating abnormal data structures are as follows: the calculated structural response deviation value is compared with the response deviation threshold. When the structural response deviation value is less than the response deviation threshold, the highly suspected disturbance fragment is marked as a pseudo-anomaly candidate and retained for subsequent pseudo-anomaly statistical analysis; when the structural response deviation value is greater than or equal to the response deviation threshold, the highly suspected disturbance fragment is transferred to the next step of feature pattern comparison, and the spectrum similarity analysis is performed: the concrete crack width, stress value of the load-bearing component and steel stress of the current highly suspected disturbance fragment are extracted to form a pseudo-anomaly candidate. The three-dimensional structural response sequence is slidingly matched with the stable three-dimensional structural response sequence composed of concrete crack width, load-bearing component stress and steel bar stress in the historical steady-state sample set; if the structural response threshold error range constraint is met in the continuous comparison segment, the current highly suspected disturbance segment is marked as a steady-state deviation; otherwise, the current highly suspected disturbance segment is marked as a highly credible anomaly segment; the water conservancy construction monitoring data corresponding to the time segment identified as a highly credible anomaly segment are recorded together with the time index, monitoring point number, structural disturbance assessment value and structural response deviation value to form a complete anomaly data structure, which serves as the input basis for the subsequent anomaly analysis and judgment process.

[0055] In this implementation plan, by introducing a three-dimensional structural response sequence comparison mechanism and combining the joint characteristics of concrete crack width, stress value of load-bearing components and steel bar stress, a sliding comparison strategy is constructed, which significantly improves the accuracy and discrimination efficiency of screening highly suspected disturbance fragments. With the support of engineering technology research and development, by comparing with the numerical range of stable structural response sequences in historical steady-state samples, pseudo-abnormal fragments are systematically eliminated and highly reliable abnormal fragments are clearly marked. At the same time, the time index, monitoring point number, structural disturbance assessment value and structural response deviation value of the highly reliable abnormal fragment are recorded together to generate a standardized abnormal data structure, which provides structured input and decision-making basis for the subsequent abnormal analysis and judgment process, ensuring that the abnormal identification process has traceability and data closure.

[0056] Specifically, based on the identified abnormal data structure, the coupling relationship between structural response and environmental disturbance is jointly analyzed, and the specific steps for constructing a dynamic imbalance index for measuring non-steady-state strength are as follows: Based on the abnormal data structure, all water conservancy construction monitoring data of the time period corresponding to the high-credible abnormal fragment are extracted. The water conservancy construction monitoring data include pore water pressure, seepage rate, atmospheric pressure, construction temperature, construction humidity, surface settlement, concrete crack width, stress value of load-bearing components, steel bar stress and structural vibration acceleration. The structural disturbance assessment value and the structural response deviation value are combined to construct a two-dimensional perspective of structure and environment, and a comprehensive analysis of the coupling mode between structural response and environmental disturbance is conducted to quantify the non-steady-state driving strength of the current time period; the square of the sum of the structural disturbance assessment value and the structural response deviation value is calculated to reflect the structure. The abnormal intensity of the cumulative response at the structural level is recorded as the structural response amplification term; the product of the surface settlement and the seepage rate is calculated, and this product is divided by the sum of the construction temperature and the minimum term, where the minimum term is a set small positive constant used for numerical stability control and to prevent calculation errors caused by the denominator approaching zero. This ratio can characterize the coupling effect between local geological disturbances and groundwater activity, and is recorded as the geological environment coupling term; the absolute value of the difference between the pore water pressure and the atmospheric pressure is calculated and added to 1, and then the natural logarithm is taken to measure the regulatory effect of abnormal external pressure changes on structural disturbances. This logarithm is recorded as the external pressure disturbance adjustment term; the structural response amplification term, the geological environment coupling term, and the external pressure disturbance adjustment term are added together to form the dynamic imbalance value corresponding to the current high-credibility abnormal segment, which serves as the key input indicator for subsequent abnormal level judgment.

[0057] The specific calculation formula for the dynamic imbalance value is:

[0058]

[0059] Where, represents the dynamic imbalance value, D represents the structural disturbance assessment value, S represents the structural response deviation value, h represents the surface settlement, v represents the seepage rate, T represents the construction temperature, represents the pore water pressure, represents the atmospheric pressure, and ε represents the minimum term.

[0060] In this embodiment, Table 2 is a dynamic imbalance value data table, which records in detail the key monitoring data and indicator calculation results of 5 high-credibility abnormal segments in the comprehensive analysis process of structural disturbance and environmental disturbance, and is used to quantify the degree of structural imbalance under unstable working conditions. Among them: the structural disturbance assessment value corresponding to high-credibility abnormal segment 1 is 1.82, the structural response deviation value is 1.65, the surface settlement is 9.80, the seepage rate is 3.10, the construction temperature is 26.50, the pore water pressure is 89.40, the atmospheric pressure is 101.80, and the dynamic imbalance value is 11.48; in high-credibility abnormal segment 2, the structural disturbance assessment value is 2.10, the structural response deviation value is 1.78, the surface settlement is 12.30, the seepage rate is 3.60, the construction temperature is 27.80, the pore water pressure is 87 .10, atmospheric pressure is 101.50, and dynamic imbalance value is 14.40; in high-confidence anomaly segment 3, the structural disturbance assessment value is 1.45, the structural response deviation value is 1.52, the surface settlement is 7.20, the seepage rate is 2.50, the construction temperature is 25.60, the pore water pressure is 90.50, the atmospheric pressure is 101.70, and the dynamic imbalance value is 8.52; in high-confidence anomaly segment 4, the structural disturbance assessment value is 2.45, the structural response deviation value is 2.30, the surface settlement is 15.10, and the seepage rate is 4.20

[0061] , the construction temperature is 29.10, the pore water pressure is 86.00, the atmospheric pressure is 101.20, and the dynamic imbalance value is 18.83; in the high-confidence anomaly fragment 5, the structural disturbance assessment value is 1.65, the structural response deviation value is 1.70, the surface settlement is 8.40, the seepage rate is 2.80, the construction temperature is 26.90, the pore water pressure is 88.60, the atmospheric pressure is 101.60, and the dynamic imbalance value is 9.71.

[0062] Table 2 Dynamic imbalance value data table

[0063] snippet D S h v T <![CDATA[P w ]]> <![CDATA[P w ]]> Q 1 1.06 0.79 10.41 0.17 27.24 128.52 101.3 6.85 2 1.47 0.73 29.40 0.22 17.79 69.97 101.3 8.68 3 1.31 1.22 26.65 0.31 20.84 101.42 101.3 6.92 4 1.22 1.06 14.25 0.27 22.33 109.24 101.3 7.56 5 0.91 1.12 13.64 0.22 24.12 54.65 101.3 8.12

[0064] like Figure 4The figure shows the distribution of dynamic imbalance values ​​and disturbance levels for high-confidence anomaly segments. It displays the dynamic imbalance values ​​and their corresponding disturbance levels for five high-confidence anomaly segments, demonstrating the system's ability to automatically identify and classify them under varying anomaly intensities. The horizontal axis represents the sample number, while the vertical axis represents the dynamic imbalance value. The color of the bars corresponds to the disturbance level, with mild, critical, and severe disturbances, respectively. As can be seen from the figure, the dynamic imbalance values ​​for samples 1 and 3 are 6.85 and 6.92, respectively, indicating mild disturbances; while the dynamic imbalance values ​​for samples 2, 4, and 5 are 8.68, 7.56, and 8.12, respectively, indicating critical disturbances. The specific imbalance value and disturbance level for each sample are clearly labeled above the bars, and the legend provides a visual mapping between color and level. This intuitively illustrates the distribution of dynamic imbalance values ​​within high-confidence anomaly segments, providing a quantitative basis for the formulation of subsequent dispatch response strategies and adjustments to sampling configurations.

[0065] In this implementation plan, a comprehensive indicator, dynamic imbalance value, was constructed by introducing structural perturbation assessment values ​​and structural response deviation values, combined with key hydraulic construction monitoring data such as surface settlement, seepage rate, construction temperature, pore water pressure, and atmospheric pressure. This indicator provides a refined means of quantifying the intensity of unsteady-state driving forces. This indicator integrates three components: a structural response amplification term, a geological environment coupling term, and an external pressure perturbation adjustment term. It systematically reflects the complex coupling relationship between structural response and environmental perturbations, effectively improving the accuracy and continuity of abnormal state characterization and providing a solid data foundation for subsequent hierarchical diagnosis and scheduling strategy formulation.

[0066] Specifically, the abnormality levels are divided according to the dynamic imbalance index, and the specific steps for updating the corresponding scheduling strategy and acquisition configuration are as follows: after calculating the dynamic imbalance value, the dynamic imbalance value and the imbalance threshold are compared in real time, and the high-credibility abnormal fragments are divided into levels; among them, the imbalance threshold includes the first-level imbalance threshold and the second-level imbalance threshold; when the dynamic imbalance value is less than or equal to the first-level imbalance threshold, the current high-credibility abnormal fragment is marked as a mild disturbance, triggering the local re-sampling logic, and performing encrypted sampling on the current monitoring point; when the dynamic imbalance value is greater than the first-level imbalance threshold and less than the second-level imbalance threshold, the current high-credibility abnormal fragment is marked as a critical disturbance, and the current monitoring point is encrypted and sampled, and the water conservancy monitoring data corresponding to the current high-credibility abnormal fragment is pushed to the supervision platform, with additional manual review prompts; when the dynamic imbalance value is greater than the first-level imbalance threshold and less than the second-level imbalance threshold, the current high-credibility abnormal fragment is marked as a critical disturbance, and the current monitoring point is encrypted and sampled, and the water conservancy monitoring data corresponding to the current high-credibility abnormal fragment is pushed to the supervision platform, with additional manual review prompts; When the dynamic imbalance value is greater than or equal to the second-level imbalance threshold, the current high-confidence abnormal fragment is marked as a severe disturbance, triggering the entire station alarm process, suspending related construction tasks, and transferring the fragment data to the abnormal tracing process; the dynamic imbalance value, abnormal level label, scheduling processing record and corresponding time index are archived to generate an abnormal event log, which is bound to the original water conservancy construction monitoring data to achieve full-process index tracing; the abnormal level, dynamic imbalance value, structural disturbance assessment value and structural response deviation value marked in the abnormal event log are synchronously written into the acquisition and scheduling configuration table for updating the sampling frequency setting, monitoring point priority sorting and comparison threshold adjustment plan, realizing adaptive scheduling optimization based on the actual abnormal evolution characteristics, and completing the closed-loop process of monitoring identification, response control and acquisition strategy.

[0067] In this implementation plan, by introducing a dynamic imbalance value and imbalance threshold division mechanism, the three abnormal levels of mild disturbance, critical disturbance and severe disturbance are clearly defined, effectively enhancing the hierarchical response capability of high-credibility abnormal fragments. Driven by the dynamic imbalance value, a linkage scheduling mechanism of local re-sampling, manual review, full-station alarm and abnormality tracing is realized, and key parameters such as dynamic imbalance value, abnormality level label, structural disturbance assessment value and structural response deviation value are archived in the abnormal event log to ensure the integrity of the whole process index traceability. By synchronously writing the log results into the collection and scheduling configuration table, dynamically adjusting the sampling frequency, monitoring point priority and comparison threshold setting, a closed-loop scheduling optimization system integrating monitoring identification, response control and collection strategy is established, which significantly improves the adaptive ability and data decision-making accuracy of water conservancy construction monitoring.

[0068] like Figure 2As shown, the second aspect of the present invention provides a multi-source data fusion water conservancy project construction monitoring data supervision system, including: a water conservancy construction monitoring data acquisition preprocessing module, a structural disturbance assessment and status marking module, a disturbance identification and abnormal sample extraction module and an abnormal analysis judgment and scheduling linkage module, wherein: the water conservancy construction monitoring data acquisition preprocessing module is used to obtain water conservancy construction monitoring data through real-time data acquisition and synchronous processing of multiple types of sensor equipment in the construction monitoring system, and preprocess the water conservancy construction monitoring data to obtain preprocessed water conservancy construction monitoring data; the structural disturbance assessment and status marking module is used to construct a sliding window based on the preprocessed water conservancy construction monitoring data, extract key structural and environmental variables, and comprehensively analyze The structural disturbance degree is divided into different disturbance state segments according to the structural disturbance degree, and the segment state labels of each time period are marked; the disturbance identification and abnormal sample extraction module is used to extract the unstable time period based on the segment state label, construct the disturbance feature sequence, identify the highly suspected disturbance fragments and analyze the response deviation between the structure and the environment, combine the three-dimensional structural response sequence with the historical steady-state samples for sliding comparison, screen the highly reliable abnormal fragments and generate the abnormal data structure; the abnormal analysis judgment and scheduling linkage module is used to jointly analyze the coupling relationship between the structural response and the environmental disturbance based on the identified abnormal data structure, construct the dynamic imbalance index for measuring the non-steady-state intensity, divide the abnormal level according to the dynamic imbalance index, and update the corresponding scheduling strategy and acquisition configuration.

[0069] In this implementation plan, a complete data supervision process is formed by integrating the water conservancy construction monitoring data acquisition and preprocessing module, the structural disturbance assessment and status marking module, the disturbance identification and abnormal sample extraction module, and the abnormal analysis, judgment, and scheduling linkage module. Supported by engineering technology research and development, the system can achieve real-time collection and unified preprocessing of water conservancy construction monitoring data, ensuring data consistency and availability; through quantitative assessment of the degree of structural disturbance and status segment marking, it can clarify the evolution characteristics of the construction status; relying on the disturbance feature sequence and structural response deviation analysis, it can accurately extract high-confidence abnormal fragments; combined with the construction of dynamic imbalance indicators, it can achieve graded response to abnormal levels and update the scheduling strategy, effectively enhancing the adaptive supervision capability of the monitoring system under complex working conditions and improving the level of risk identification and control driven by data.

[0070] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0071] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for supervising water conservancy project construction monitoring data by fusion of multi-source data, characterized in that: The following steps are involved: S1, acquiring water conservancy construction monitoring data by real-time data collection and synchronous processing of multiple types of sensor equipment in the construction monitoring system, and preprocessing the water conservancy construction monitoring data to obtain preprocessed water conservancy construction monitoring data; S2, based on the pre-processed water conservancy construction monitoring data, constructs a sliding window, extracts key structural and environmental variables, comprehensively analyzes the structural disturbance degree, divides different disturbance state segments according to the structural disturbance degree, and marks the segment state labels for each time period; S3, extracts unstable time periods based on segment state labels, constructs disturbance feature sequences, identifies highly suspected disturbance segments, and analyzes the response deviation between the structure and the environment. A sliding comparison is performed between the three-dimensional structure response sequence and historical steady-state samples to screen highly reliable abnormal segments and generate abnormal data structures. S4, based on the identified abnormal data structure, jointly analyzes the coupling relationship between structural response and environmental disturbance, constructs a dynamic imbalance index for measuring the intensity of non-steady-state, divides the abnormality level according to the dynamic imbalance index, and updates the corresponding scheduling strategy and acquisition configuration.

2. The method for supervising water conservancy project construction monitoring data based on multi-source data fusion according to claim 1, characterized in that: The specific steps for obtaining water conservancy construction monitoring data by real-time data collection and synchronous processing of multiple types of sensor equipment in the construction monitoring system are as follows: Through real-time data collection and synchronous processing of multiple types of sensor equipment in the construction monitoring system, water conservancy construction monitoring data is obtained. The water conservancy construction monitoring data includes pore water pressure, seepage rate, atmospheric pressure, construction temperature, construction humidity, surface settlement, concrete crack width, stress value of load-bearing components, steel stress, and structural vibration acceleration; among them, the pore water pressure is obtained by reading the liquid static pressure changes collected by the piezometers buried in the dam foundation and slopes; the seepage rate is obtained by reading the flow rate conversion result output by the seepage pressure difference sensor; the atmospheric pressure is obtained by reading the real-time measurement value of the air pressure module installed in the on-site meteorological unit; and the atmospheric pressure is obtained by the environmental sensor. The construction temperature and humidity are obtained by using the temperature channel and humidity channel data output by the sensing node; the surface settlement is obtained by reading the coordinate change information of the measuring point of the global navigation satellite system and combining it with the elevation difference extracted from the leveling measurement; the concrete crack width is obtained by collecting the displacement measurement value between the two points of the crack sensor; the stress value of the load-bearing component is obtained by reading the electrical signal collected by the stress sensor embedded in the load-bearing structure and calibrating it. The steel bar stress is obtained by collecting the data of the strain gauge on the steel bar surface and combining it with the steel bar elastic modulus conversion; the structural vibration acceleration is obtained by reading the instantaneous acceleration value output by the triaxial acceleration sensor.

3. The method for supervising water conservancy project construction monitoring data based on multi-source data fusion according to claim 1, characterized in that: The specific steps of preprocessing the water conservancy construction monitoring data to obtain the preprocessed water conservancy construction monitoring data are as follows: Through the collaborative detection of the standard deviation outlier detection method based on sliding windows and the isolation forest algorithm, the sudden changes and link abnormal data in pore water pressure, seepage rate and structural vibration acceleration are identified and eliminated; by utilizing the combined completion mechanism of the time series linear interpolation method and the spline interpolation algorithm, the missing fields in surface settlement, construction humidity and concrete crack width are completed in time series; through the joint modeling strategy of fusing the exponential weighted sliding average and the local regression algorithm, the trend fitting and high-frequency noise suppression of the construction temperature, steel bar stress and load-bearing component stress values ​​are performed; by adopting the cascade transformation of the power function transformation and the maximum and minimum normalization algorithm, the distribution adjustment and numerical compression of the water conservancy construction monitoring data are carried out, completing the unified interval reconstruction and normalization processing of the water conservancy construction monitoring data.

4. The method for supervising water conservancy project construction monitoring data based on multi-source data fusion according to claim 1, characterized in that: The specific steps of constructing a sliding window based on pre-processed water conservancy construction monitoring data, extracting key structural and environmental variables, and comprehensively analyzing the degree of structural disturbance are as follows: The pre-processed time series of pore water pressure, seepage rate, atmospheric pressure, construction temperature, construction humidity, surface settlement, concrete crack width, stress value of load-bearing components, steel bar stress and structural vibration acceleration are aligned according to a unified sampling time and merged according to the monitoring point number to form a multidimensional data structure with a unified temporal and spatial index. A sliding window of fixed length is defined in a multidimensional data structure. The concrete crack width, stress value of the load-bearing component, steel stress, pore water pressure, atmospheric pressure, construction temperature and construction humidity within the sliding window are extracted. Combined with the crack width threshold, the disturbance degree of the water conservancy project structure under complex construction and environmental conditions is evaluated: the square of the concrete crack width is divided by the crack width threshold, the absolute value of the difference between the stress value of the load-bearing component and the stress of the steel bar is calculated, and the sum of this ratio and the absolute value is multiplied by the structural weight to obtain the first part; the absolute value of the difference between the pore water pressure and the atmospheric pressure is calculated, and the sum of the construction temperature, construction humidity and the minimum term is calculated, and the absolute value is divided by the ratio of the sum and multiplied by the environmental weight to obtain the second part; the first and second parts are added together to obtain the structural disturbance assessment value.

5. The method for supervising water conservancy project construction monitoring data based on multi-source data fusion according to claim 1, characterized in that: The specific steps of dividing different disturbance state segments according to the degree of structural disturbance and marking the segment state labels of each time period are as follows: The structural disturbance assessment value within each sliding window is calculated in real time, and the structural disturbance assessment value is compared with the structural disturbance threshold. The structural disturbance threshold includes the first-level structural disturbance threshold and the second-level structural disturbance threshold: when the structural disturbance assessment value is less than or equal to the first-level structural disturbance threshold, the current time period is marked as a steady-state section, and the baseline update strategy is automatically triggered. The original water conservancy construction monitoring data in the current window is incrementally updated in the steady-state sample set, and statistical features are archived; when the structural disturbance assessment value is greater than the first-level structural disturbance threshold and less than the second-level structural disturbance threshold, the current time period is marked as a transition section, the delayed confirmation mechanism is activated, all water conservancy construction monitoring data in the current window is retained, and a time buffer is set for subsequent state evolution trend judgment; when the structural disturbance assessment value is greater than or equal to the second-level structural disturbance threshold, the current time period is marked as an unstable section, the high-frequency re-sampling logic is called, and the enhanced sampling mode is enabled for the covered monitoring points in the subsequent time period. At the same time, the water conservancy construction monitoring data in the current sliding window is pushed to the anomaly identification processing process; The segment mark corresponding to each time period is used as the segment status label and attached to the metadata of the current sliding window. The label contains the status category, time segment range and monitoring point number, and is retained together with the time index and used as the input index and scheduling basis for the subsequent recognition process.

6. The method for supervising water conservancy project construction monitoring data based on multi-source data fusion according to claim 1, characterized in that: The specific steps of extracting unstable time periods based on segment state labels, constructing disturbance feature sequences, identifying highly suspected disturbance segments, and analyzing the response deviation between the structure and the environment are as follows: Extract the time period where the segment status label is marked as an unstable segment, obtain the corresponding pore water pressure, seepage rate and structural vibration acceleration within the time period, and construct a pseudo-anomaly candidate sample set by combining the time index and monitoring point number contained in the status label; In the pseudo-anomaly candidate sample set, a sliding time series is constructed around pore water pressure, seepage rate and structural vibration acceleration, and three types of statistical features are extracted: standard deviation, jump amplitude and number of fluctuations. After normalizing each statistical feature, it forms a feature vector and inputs it into the isolation forest algorithm to calculate the corresponding isolation value. The isolation value is compared with the isolation threshold in real time, and samples with isolation values ​​exceeding the isolation threshold are screened out and recorded as highly suspected disturbance fragments. For highly suspected disturbance fragments, the degree of deviation between their internal structural response and the external environmental background is further quantified; the absolute value of the difference between the stress value of the load-bearing component and the stress of the steel bar is divided by the sum of the concrete crack width and the minimum term, and the ratio is recorded as the structural coordination term; the absolute value of the difference between the pore water pressure and the atmospheric pressure is calculated, added to 1, and the logarithm is taken. The structural vibration acceleration is divided by this logarithmic value plus 1, and this ratio is added to 1 as the disturbance amplification term; the structural coordination term is multiplied by the disturbance amplification term to obtain the structural response deviation value.

7. The method for supervising water conservancy project construction monitoring data based on multi-source data fusion according to claim 1, characterized in that: The specific steps of performing sliding comparison between the three-dimensional structure response sequence and the historical steady-state samples, screening high-confidence abnormal fragments and generating abnormal data structures are as follows: The calculated structural response deviation value is compared with the response deviation threshold. When the structural response deviation value is less than the response deviation threshold, the highly suspected disturbance segment is marked as a pseudo-anomaly candidate and retained for subsequent pseudo-anomaly statistical analysis. When the structural response deviation value is greater than or equal to the response deviation threshold, the highly suspected disturbance segment is transferred to the next step of characteristic pattern comparison and a spectrum similarity analysis is performed: the concrete crack width, load-bearing component stress value and steel bar stress of the current highly suspected disturbance segment are extracted to form a three-dimensional structural response sequence, and a sliding match is performed with the stable three-dimensional structural response sequence composed of the concrete crack width, load-bearing component stress value and steel bar stress in the historical steady-state sample set. If the structural response threshold error range constraint is met in the continuous comparison segment, the current highly suspected disturbance segment is marked as a steady-state deviation; otherwise, the current highly suspected disturbance segment is marked as a high-confidence anomaly segment. The water conservancy construction monitoring data corresponding to the time segments identified as high-confidence abnormal segments are recorded together with the time index, monitoring point number, structural disturbance assessment value and structural response deviation value to form a complete abnormal data structure, which serves as the input basis for the subsequent abnormal analysis and judgment process.

8. The method for supervising water conservancy project construction monitoring data based on multi-source data fusion according to claim 1, characterized in that: The specific steps of jointly analyzing the coupling relationship between structural response and environmental disturbance based on the identified abnormal data structure and constructing a dynamic imbalance index for measuring the non-steady-state intensity are as follows: Based on the abnormal data structure, all water conservancy construction monitoring data corresponding to the time period of the high-credibility abnormal fragment is extracted. The structural disturbance assessment value and the structural response deviation value are combined to comprehensively analyze the coupling mode between the structural response and the environmental disturbance, and quantify the non-steady-state driving intensity of the current time period. Calculate the square of the sum of the structural disturbance assessment value and the structural response deviation value, and record it as the structural response amplification term; calculate the product of the surface settlement and the seepage rate, divide this product by the construction temperature plus the minimum term, and record the ratio as the geological environment coupling term; calculate the absolute value of the difference between the pore water pressure and the atmospheric pressure, add 1, and take the logarithm of this value, and record this logarithm as the external pressure disturbance adjustment term; add the structural response amplification term, the geological environment coupling term, and the external pressure disturbance adjustment term to obtain the dynamic imbalance value.

9. The method for supervising water conservancy project construction monitoring data based on multi-source data fusion according to claim 1, characterized in that: The specific steps of classifying abnormal levels according to dynamic imbalance indicators and updating corresponding scheduling strategies and collection configurations are as follows: After the dynamic imbalance value is calculated, the dynamic imbalance value and the imbalance threshold are compared in real time, and the high-credibility abnormal fragments are graded; among them, the imbalance threshold includes the first-level imbalance threshold and the second-level imbalance threshold; when the dynamic imbalance value is less than or equal to the first-level imbalance threshold, the current high-credibility abnormal fragment is marked as a mild disturbance, triggering the local re-sampling logic, and encrypting the sampling of the current monitoring point; when the dynamic imbalance value is greater than the first-level imbalance threshold and less than the second-level imbalance threshold, the current high-credibility abnormal fragment is marked as a critical disturbance, encrypting the sampling of the current monitoring point, and pushing the water conservancy monitoring data corresponding to the current high-credibility abnormal fragment to the supervision platform, with additional manual review prompts; when the dynamic imbalance value is greater than or equal to the second-level imbalance threshold, the current high-credibility abnormal fragment is marked as a severe disturbance, triggering the whole-station alarm process, suspending related construction tasks, and transferring the fragment data to the abnormal tracing process; The dynamic imbalance value, abnormality level label, scheduling processing record and corresponding time index are archived to generate an abnormal event log, which is bound to the original water conservancy construction monitoring data to realize the index traceability of the whole process; the abnormality level, dynamic imbalance value, structural disturbance assessment value and structural response deviation value marked in the abnormal event log are synchronously written into the acquisition and scheduling configuration table to update the sampling frequency setting, monitoring point priority sorting and comparison threshold adjustment plan, realize adaptive scheduling optimization based on the actual abnormal evolution characteristics, and complete the closed-loop process of monitoring identification, response control and acquisition strategy.

10. A water conservancy project construction monitoring data supervision system integrating multi-source data, characterized by: include: Water conservancy construction monitoring data acquisition and preprocessing module, structural disturbance assessment and status marking module, disturbance identification and abnormal sample extraction module, and abnormal analysis, judgment and scheduling linkage module, including: The water conservancy construction monitoring data acquisition and preprocessing module is used to acquire water conservancy construction monitoring data through real-time data acquisition and synchronous processing of multiple types of sensor equipment in the construction monitoring system, and preprocess the water conservancy construction monitoring data to obtain preprocessed water conservancy construction monitoring data; The structural disturbance assessment and status marking module is used to construct a sliding window based on pre-processed water conservancy construction monitoring data, extract key structural and environmental variables, comprehensively analyze the degree of structural disturbance, divide different disturbance state sections according to the degree of structural disturbance, and mark the section status labels of each time period; The disturbance identification and abnormal sample extraction module is used to extract unstable time periods based on segment state labels, construct disturbance feature sequences, identify highly suspected disturbance segments, and analyze the response deviation between the structure and the environment. It combines the three-dimensional structure response sequence with historical steady-state samples for sliding comparison, screens highly reliable abnormal segments, and generates abnormal data structures. The abnormal analysis, judgment and scheduling linkage module is used to jointly analyze the coupling relationship between structural response and environmental disturbance based on the identified abnormal data structure, construct a dynamic imbalance index for measuring the intensity of non-steady-state, divide the abnormality level according to the dynamic imbalance index, and update the corresponding scheduling strategy and acquisition configuration.

Images